| ▲ | fathermarz 3 hours ago | |
Completely agree. This is a harness problem, not a model problem. The model is rarely the issue these days | ||
| ▲ | 827a an hour ago | parent | next [-] | |
More-so an environment problem. An agent doing staging or development tasks should never be able to get access to prod API credentials, period. Agents which do have access to prod should have their every interaction with the outside world audited by a human. | ||
| ▲ | bigstrat2003 2 hours ago | parent | prev [-] | |
No, this is a "being stupid enough to trust an LLM" problem. They are not trustworthy, and you must not ever let them take automated actions. Anyone who does that is irresponsible and will sooner or later learn the error of their ways, as this person did. | ||